List your company

Uncertainty Quantification on InfoSeek (val)

14.7AccuracyPE
10.0211.23512.4513.665May 28, 2026

Evaluation results

MethodLinks
PELLM=LLaVA1.5-7B, Retriever=BM25+MLM2026.0514.772.9
P(True)LLM=LLaVA1.5-7B, Retriever=BM25+MLM2026.0514.761.4
Ecc.LLM=LLaVA1.5-7B, Retriever=BM25+MLM2026.0514.771.7
Img. Per.LLM=LLaVA1.5-7B, Retriever=BM25+MLM2026.0514.739.7
LARS_BaseLLM=LLaVA1.5-7B, Retriever=BM25+MLM2026.0514.775.2
LARS_RetLLM=LLaVA1.5-7B, Retriever=BM25+MLM2026.0514.779.1
LeMUQLLM=LLaVA1.5-7B, Retriever=BM25+MLM2026.0514.785.3
PELLM=Qwen3-VL-4B, Retriever=BM252026.0514.277
P(True)LLM=Qwen3-VL-4B, Retriever=BM252026.0514.273.4
Ecc.LLM=Qwen3-VL-4B, Retriever=BM252026.0514.266.7
Img. Per.LLM=Qwen3-VL-4B, Retriever=BM252026.0514.229.4
LARS_BaseLLM=Qwen3-VL-4B, Retriever=BM252026.0514.276.5
LARS_RetLLM=Qwen3-VL-4B, Retriever=BM252026.0514.285.8
LeMUQLLM=Qwen3-VL-4B, Retriever=BM252026.0514.288.8
PELLM=Qwen3-VL-4B, Retriever=BM25+MLM2026.051474.9
P(True)LLM=Qwen3-VL-4B, Retriever=BM25+MLM2026.051474
Ecc.LLM=Qwen3-VL-4B, Retriever=BM25+MLM2026.051462.9
Img. Per.LLM=Qwen3-VL-4B, Retriever=BM25+MLM2026.051429.1
LARS_BaseLLM=Qwen3-VL-4B, Retriever=BM25+MLM2026.051477.1
LARS_RetLLM=Qwen3-VL-4B, Retriever=BM25+MLM2026.051484.5
LeMUQLLM=Qwen3-VL-4B, Retriever=BM25+MLM2026.051489.8
PELLM=Qwen3-VL-4B, Retriever=EVAC.2026.0512.781.3
P(True)LLM=Qwen3-VL-4B, Retriever=EVAC.2026.0512.771.4
Ecc.LLM=Qwen3-VL-4B, Retriever=EVAC.2026.0512.770.5
Img. Per.LLM=Qwen3-VL-4B, Retriever=EVAC.2026.0512.732.1
LARS_BaseLLM=Qwen3-VL-4B, Retriever=EVAC.2026.0512.782.5
LARS_RetLLM=Qwen3-VL-4B, Retriever=EVAC.2026.0512.789
LeMUQLLM=Qwen3-VL-4B, Retriever=EVAC.2026.0512.791.3
PELLM=LLaVA1.5-7B, Retriever=BM252026.0511.875.6
P(True)LLM=LLaVA1.5-7B, Retriever=BM252026.0511.864.5
Ecc.LLM=LLaVA1.5-7B, Retriever=BM252026.0511.874.5
Img. Per.LLM=LLaVA1.5-7B, Retriever=BM252026.0511.841.4
LARS_BaseLLM=LLaVA1.5-7B, Retriever=BM252026.0511.876.2
LARS_RetLLM=LLaVA1.5-7B, Retriever=BM252026.0511.882.9
LeMUQLLM=LLaVA1.5-7B, Retriever=BM252026.0511.883.3
PELLM=LLaVA1.5-7B, Retriever=EVAC.2026.0510.277.5
P(True)LLM=LLaVA1.5-7B, Retriever=EVAC.2026.0510.264.5
Ecc.LLM=LLaVA1.5-7B, Retriever=EVAC.2026.0510.275.5
Img. Per.LLM=LLaVA1.5-7B, Retriever=EVAC.2026.0510.240.9
LARS_BaseLLM=LLaVA1.5-7B, Retriever=EVAC.2026.0510.275.2
LARS_RetLLM=LLaVA1.5-7B, Retriever=EVAC.2026.0510.282.3
LeMUQLLM=LLaVA1.5-7B, Retriever=EVAC.2026.0510.285.4